---
title: "KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual"
description: "The KEIS@JUST team entered OffensEval 2020 (SemEval-2020 Task 12), a shared task on detecting… 44 references, cited by 1 paper here."
authors: ["Saja Tawalbeh", "Mahmoud Hammad", "Mohammad AL-Smadi"]
year: 2020
venue: "Proceedings of the Fourteenth Workshop on Semantic Evaluation"
source: "https://aclanthology.org/2020.semeval-1.269/"
doi: "10.18653/v1/2020.semeval-1.269"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tawalbeh-2020-keis-just-semeval-2020-task/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tawalbeh-2020-keis-just-semeval-2020-task/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/8/) / KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT

# KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT

**Authors:** [Saja Tawalbeh](https://md.research.elamur.ai/free/en/authors/saja-tawalbeh/), Mahmoud Hammad and [Mohammad AL-Smadi](https://md.research.elamur.ai/free/en/authors/mohammad-al-smadi/) · **Year:** 2020 · **Venue:** [Proceedings of the Fourteenth Workshop on Semantic Evaluation](https://md.research.elamur.ai/free/en/venues/semeval/) ([SemEval 2020](https://md.research.elamur.ai/free/en/venues/semeval/2020/)) · **Publisher:** [International Committee on Computational Linguistics (ICCL)](https://md.research.elamur.ai/free/en/publishers/international-committee-on-computational-linguistics-iccl/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.semeval-1.269/) · [PDF](https://aclanthology.org/2020.semeval-1.269.pdf) · [DOI 10.18653/v1/2020.semeval-1.269](https://doi.org/10.18653/v1/2020.semeval-1.269) · [OpenAlex](https://openalex.org/W3024331991)

**Citations:** 13 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The KEIS@JUST team entered OffensEval 2020 (SemEval-2020 Task 12), a shared task on detecting offensive tweets in Arabic, English, Danish, Greek and Turkish. They competed in every language and subtask except English sub-task A. They used two systems:
- **KEIS-BiGRUCNN** (Arabic sub-task A, English sub-tasks B and C) is a weighted ensemble. One branch is a Bi-GRU and the other a multi-filter CNN. Both inject Gaussian noise after the embedding layer. Their sigmoid outputs are combined with fixed weights.
- **KEIS-BERT-Bi** (Danish, Greek and Turkish sub-task A) stacks Bi-LSTM/Bi-GRU layers and global average pooling on top of multilingual cased BERT.

Inputs were AraVec embeddings for Arabic and word2vec for English, after cleaning the tweets. For Arabic only, the authors enlarged the training data by swapping frequent words for embedding-based synonyms. This raised validation macro-F1 by about four points.

On the test set, Arabic was the strongest result, at 11th of 56 teams. The English B and C subtasks performed poorly. The paper mainly shows that cheap augmentation and simple ensembling help a lower-resource language like Arabic.

## Key points
- Arabic validation macro-F1 rose with augmentation for every model:
  - KEIS-BiGRU: 83.6% → 87.6%
  - KEIS-CNN: 83.5% → 87.3%
  - KEIS-BiGRUCNN: 83.8% → 87.9%
- Test macro-F1 and ranks:

  | Language / subtask | Macro-F1 | Rank |
  |---|---|---|
  | Arabic A | 86.55% | 11th of 56 |
  | Danish A | 76.1% | 12th of 39 |
  | Greek A | 77.3% | 28th |
  | Turkish A | 73.3% | 32nd |
  | English B | 27.7% | — |
  | English C | 48.17% | — |

  The introduction reports Greek differently; the figures above follow the results tables.
- Ensemble settings:
  - weights: 0.4 for KEIS-CNN, 0.6 for KEIS-BiGRU
  - optimizer: amsgrad, learning rate 0.01
  - training: batch size 128, 20 epochs, L2 regularization 0.01
- CNN branch: four Conv2D layers with filter widths 1, 3, 5 and 7, 36 filters each, then max-pooling and concatenation. Bi-GRU branch: 128 units, Gaussian noise 0.1, global average pooling, dense layer of 35.
- Preprocessing:
  - removed URLs, mentions, punctuation, emojis and letter elongation
  - for Arabic, also removed digits and Latin characters
  - training used early stopping, checkpoints and learning-rate reduction

## Interesting ideas
- Augment scarce training data by replacing the most frequent words with their nearest neighbours in a pretrained embedding space; this is a nearly free way to grow a small labelled set.
- Combine two different architectures (a sequence model and a local n-gram detector) through fixed output weights chosen on validation data, instead of a learned meta-model; this keeps the combination transparent and easy to tune.
- Add small Gaussian noise directly to word embeddings during training as a regularizer, which makes the model less brittle to rare or noisy words.
- Choose the approach per language by resource availability: dedicated embeddings plus augmentation where native vectors exist, and multilingual BERT elsewhere.
- Validation and test scores can diverge sharply; for English sub-task B, 48.3% on validation fell to 27.7% on test, which exposes a distribution shift that validation alone hid.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): Neighbour-based lexical swaps could multiply silver sentences for the tagger and parser, but each swap should be checked against a negative control so labels are not silently corrupted.
- **I2** (learn): Witness parsers voting on silver trees could carry explicit, validation-tuned trust weights, so every agreement decision stays explainable.
- **I3** (tree): gparse could add embedding noise during training to tolerate typos and informal input, with a measurable effect on LAS.
- **I4** (tokens): Lexical resources in crate en could follow a similar tiered fallback, using curated morphology first and a generic subword model only for unknown forms.
- **I5** (answer): School-test and fable-QA readers should always be scored on a truly held-out set alongside the development set, so overfitting to familiar question styles shows up early.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Jordan University of Science and Technology](https://md.research.elamur.ai/free/en/universities/jordan-university-of-science-and-technology/) — University, Irbid, Jordan · 15 works · 1,840 citations
- [University of Jordan](https://md.research.elamur.ai/free/en/universities/university-of-jordan/) — University, Amman, Jordan · 14 works · 171 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works

## Cite

Cite as: Saja Tawalbeh, Mahmoud Hammad and Mohammad AL-Smadi. 2020. KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT. Proceedings of the Fourteenth Workshop on Semantic Evaluation.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{tawalbeh2020keis,
  title = {{KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT}},
  author = {Saja Tawalbeh, Mahmoud Hammad and Mohammad AL-Smadi},
  booktitle = {Proceedings of the Fourteenth Workshop on Semantic Evaluation},
  year = {2020},
  doi = {10.18653/v1/2020.semeval-1.269},
  url = {https://doi.org/10.18653/v1/2020.semeval-1.269}
}
```

- [← previous Bert Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets](https://md.research.elamur.ai/free/en/papers/harrag-2020-bert-transformer-model-detecting-arabic/)
- [next → Lemmatization and POS-tagging process by using joint learning approach. Experimental results on Classical Armenian, Old Georgian, and Syriac](https://md.research.elamur.ai/free/en/papers/gorene-2020-lemmatization-pos-tagging-process-joint/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/8/)

## References

44 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Kareem E Abdelfatah, Gabriel Terejanu, and Ayman A Alhelbawy. 2017. Unsupervised detection of violent content in arabic social media. Computer Science & Information Technology (CS & IT), 7. [find](https://scholar.google.com/scholar?q=Kareem+E+Abdelfatah%2C+Gabriel+Terejanu%2C+and+Ayman+A+Alhelbawy%2E+2017%2E+Unsupervised+detection+of+violent+content+in+arabic+social+media%2E+Computer+Science+%26+Information+Technology+%28CS+%26+IT%29%2C+7%2E)
2. Ehab A Abozinadah, Alex V Mbaziira, and J Jones. 2015. Detection of abusive accounts with arabic tweets. Int. J. Knowl. Eng.-IACSIT, 1(2):113–119. [↗](https://doi.org/10.7763/ijke.2015.v1.19)
3. Areej Al-Hassan and Hmood Al-Dossari. 2019. Detection of hate speech in social networks: a survey on multilingual corpus. In 6th International Conference on Computer Science and Information Technology. [find](https://scholar.google.com/scholar?q=Areej+Al%2DHassan+and+Hmood+Al%2DDossari%2E+2019%2E+Detection+of+hate+speech+in+social+networks%3A+a+survey+on+multilingual+corpus%2E+In+6th+International+Conference+on+Computer+Science+and+Information+Technology)
4. Azalden Alakrot, Liam Murray, and Nikola S Nikolov. 2018. Towards accurate detection of offensive language in online communication in arabic. Procedia computer science, 142:315–320. [find](https://scholar.google.com/scholar?q=Azalden+Alakrot%2C+Liam+Murray%2C+and+Nikola+S+Nikolov%2E+2018%2E+Towards+accurate+detection+of+offensive+language+in+online+communication+in+arabic%2E+Procedia+computer+science%2C+142%3A315%E2%80%93320%2E)
5. Ayman Alhelbawy, Poesio Massimo, and Udo Kruschwitz. 2016. [Towards a corpus of violence acts in arabic social media](https://md.research.elamur.ai/free/en/papers/alhelbawy-2016-corpus-violence-acts-arabic-social/). In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 1627–1631. Shiladitya Bhattacharya, Siddharth Singh, Ritesh Kumar, Akanksha Bansal, Akash Bhagat, Yogesh Dawer, Bornini Lahiri, and Atul Kr.
6. Ojha. 2020. Developing a multilingual annotated corpus of misogyny and aggression. [find](https://scholar.google.com/scholar?q=Ojha%2E+2020%2E+Developing+a+multilingual+annotated+corpus+of+misogyny+and+aggression%2E)
7. Çağrı Çöltekin. 2020. [A Corpus of Turkish Offensive Language on Social Media](https://md.research.elamur.ai/free/en/papers/coltekin-2020-corpus-turkish-offensive-language-social/). In Proceedings of the 12th International Conference on Language Resources and Evaluation. ELRA.
8. Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. [↗](https://arxiv.org/abs/1412.3555)
9. Belur V Dasarathy and Belur V Sheela. 1979. A composite classifier system design: concepts and methodology. Proceedings of the IEEE, 67(5):708–713. [↗](https://doi.org/10.1109/proc.1979.11321)
10. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. [Automated hate speech detection and the problem of offensive language](https://md.research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/). In Eleventh international aaai conference on web and social media. [↗](https://doi.org/10.48550/arxiv.1703.04009)
11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805. [↗](https://arxiv.org/abs/1810.04805)
12. Heba Elfardy and Mona Diab. 2013. [Sentence level dialect identification in arabic](https://md.research.elamur.ai/free/en/papers/elfardy-2013-sentence-level-dialect-identification-arabic/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 456–461.
13. Darja Fišer, Tomaž Erjavec, and Nikola Ljubešić. 2017. Legal framework, dataset and annotation schema for socially unacceptable online discourse practices in slovene. In Proceedings of the first workshop on abusive language online, pages 46–51. [find](https://scholar.google.com/scholar?q=Darja+Fis%CC%8Cer%2C+Tomaz%CC%8C+Erjavec%2C+and+Nikola+Ljubes%CC%8Cic%CC%81%2E+2017%2E+Legal+framework%2C+dataset+and+annotation+schema+for+socially+unacceptable+online+discourse+practices+in+slovene%2E+In+Proceedings+of+the+first+w)
14. Paula Fortuna and Sérgio Nunes. 2018. A Survey on Automatic Detection of Hate Speech in Text. ACM Computing Surveys (CSUR), 51(4):85. [↗](https://doi.org/10.1145/3232676)
15. Antigoni-Maria Founta, Constantinos Djouvas, Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Gianluca Stringhini, Athena Vakali, Michael Sirivianos, and Nicolas Kourtellis. 2018. Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior. arXiv preprint arXiv:1802.00393. [↗](https://arxiv.org/abs/1802.00393)
16. Jiahui Han, Shengtan Wu, and Xinyu Liu. 2019. jhan014 at SemEval-2019 task 6: Identifying and categorizing offensive language in social media. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 652–656, Minneapolis, Minnesota, USA, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiahui+Han%2C+Shengtan+Wu%2C+and+Xinyu+Liu%2E+2019%2E+jhan014+at+SemEval%2D2019+task+6%3A+Identifying+and+categorizing+offensive+language+in+social+media%2E+In+Proceedings+of+the+13th+International+Workshop+on+Sema)
17. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. [↗](https://doi.org/10.1162/neco.1997.9.8.1735)
18. Yoon Kim. 2014. [Convolutional neural networks for sentence classification](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/). arXiv preprint arXiv:1408.5882. Ritesh Kumar, Atul Kr. [↗](https://arxiv.org/abs/1408.5882)
19. Ojha, Shervin Malmasi, and Marcos Zampieri. 2018. [Benchmarking Aggression Identification in Social Media](https://md.research.elamur.ai/free/en/papers/kumar-2018-benchmarking-aggression-identification-social-media/). In Proceedings of the First Workshop on Trolling, Aggression and Cyberbulling (TRAC), Santa Fe, USA.
20. Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I Sánchez. 2017. A survey on deep learning in medical image analysis. Medical image analysis, 42:60–88. [↗](https://doi.org/10.1016/j.media.2017.07.005)
21. Ping Liu, Wen Li, and Liang Zou. 2019. [NULI at SemEval-2019 task 6: Transfer learning for offensive language detection using bidirectional transformers](https://md.research.elamur.ai/free/en/papers/liu-2019-nuli-semeval-2019-task-6/). In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 87–91, Minneapolis, Minnesota, USA, June. Association for Computational Linguistics.
22. Debanjan Mahata, Haimin Zhang, Karan Uppal, Yaman Kumar, Rajiv Ratn Shah, Simra Shahid, Laiba Mehnaz, and Sarthak Anand. 2019. MIDAS at SemEval-2019 task 6: Identifying offensive posts and targeted offense from twitter. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 683–690, Minneapolis, Minnesota, USA, June. Association for Computational Linguistics. Shervin Malmasi and Marcos Zampieri. arXiv:1712.06427. 2017. Detecting hate speech in social media. arXiv preprint Shervin Malmasi and Marcos Zampieri. 2018. Challenges in Discriminating Profanity from Hate Speech. Journal of Experimental & Theoretical Artificial Intelligence, 30:1–16. [↗](https://arxiv.org/abs/1712.06427)
23. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Advances in neural information processing systems, pages 3111–3119. [↗](https://doi.org/10.48550/arxiv.1310.4546)
24. Hamdy Mubarak, Kareem Darwish, and Walid Magdy. 2017. [Abusive language detection on arabic social media](https://md.research.elamur.ai/free/en/papers/mubarak-2017-abusive-language-detection-arabic-social/). In Proceedings of the First Workshop on Abusive Language Online, pages 52–56.
25. Hamdy Mubarak, Ammar Rashed, Kareem Darwish, Younes Samih, and Ahmed Abdelali. 2020. [Arabic offensive language on twitter: Analysis and experiments](https://md.research.elamur.ai/free/en/papers/mubarak-2021-arabic-offensive-language-twitter-analysis/). arXiv preprint arXiv:2004.02192. [↗](https://arxiv.org/abs/2004.02192)
26. Hala Mulki, Hatem Haddad, Chedi Bechikh Ali, and Halima Alshabani. 2019. [L-hsab: A levantine twitter dataset for hate speech and abusive language](https://md.research.elamur.ai/free/en/papers/mulki-2019-l-hsab-levantine-twitter-dataset/). In Proceedings of the Third Workshop on Abusive Language Online, pages 111–118.
27. Andraž Pelicon, Matej Martinc, and Petra Kralj Novak. 2019. Embeddia at SemEval-2019 task 6: Detecting hate with neural network and transfer learning approaches. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 604–610, Minneapolis, Minnesota, USA, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Andraz%CC%8C+Pelicon%2C+Matej+Martinc%2C+and+Petra+Kralj+Novak%2E+2019%2E+Embeddia+at+SemEval%2D2019+task+6%3A+Detecting+hate+with+neural+network+and+transfer+learning+approaches%2E+In+Proceedings+of+the+13th+Internatio)
28. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543. [↗](https://doi.org/10.3115/v1/d14-1162)
29. Matthew E Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. [Deep contextualized word representations](https://md.research.elamur.ai/free/en/papers/peters-2018-deep-contextualized-word-representations/). arXiv preprint arXiv:1802.05365. [↗](https://arxiv.org/abs/1802.05365)
30. Zeses Pitenis, Marcos Zampieri, and Tharindu Ranasinghe. 2020. [Offensive language identification in greek](https://md.research.elamur.ai/free/en/papers/pitenis-2020-offensive-language-identification-greek/). arXiv preprint arXiv:2003.07459. [↗](https://arxiv.org/abs/2003.07459)
31. Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, Marcos Zampieri, and Preslav Nakov. 2020a. A Large-Scale Weakly Supervised Dataset for Offensive Language Identification. In arxiv. [find](https://scholar.google.com/scholar?q=Sara+Rosenthal%2C+Pepa+Atanasova%2C+Georgi+Karadzhov%2C+Marcos+Zampieri%2C+and+Preslav+Nakov%2E+2020a%2E+A+Large%2DScale+Weakly+Supervised+Dataset+for+Offensive+Language+Identification%2E+In+arxiv%2E)
32. Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, Marcos Zampieri, and Preslav Nakov. 2020b. A large-scale semi-supervised dataset for offensive language identification. [find](https://scholar.google.com/scholar?q=Sara+Rosenthal%2C+Pepa+Atanasova%2C+Georgi+Karadzhov%2C+Marcos+Zampieri%2C+and+Preslav+Nakov%2E+2020b%2E+A+large%2Dscale+semi%2Dsupervised+dataset+for+offensive+language+identification%2E)
33. Björn Ross, Michael Rist, Guillermo Carbonell, Benjamin Cabrera, Nils Kurowsky, and Michael Wojatzki. 2017. Measuring the reliability of hate speech annotations: The case of the european refugee crisis. arXiv preprint arXiv:1701.08118. [↗](https://arxiv.org/abs/1701.08118)
34. Anna Schmidt and Michael Wiegand. 2017. [A Survey on Hate Speech Detection Using Natural Language Processing](https://md.research.elamur.ai/free/en/papers/schmidt-2017-survey-hate-speech-detection-natural/). In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media. Association for Computational Linguistics, pages 1–10, Valencia, Spain.
35. Gudbjartur Ingi Sigurbergsson and Leon Derczynski. 2020. [Offensive Language and Hate Speech Detection for Danish](https://md.research.elamur.ai/free/en/papers/sigurbergsson-2020-offensive-language-hate-speech-detection/). In Proceedings of the 12th Language Resources and Evaluation Conference. ELRA. [↗](https://doi.org/10.48550/arxiv.1908.04531)
36. Abu Bakr Soliman, Kareem Eissa, and Samhaa R El-Beltagy. 2017. Aravec: A set of arabic word embedding models for use in arabic nlp. Procedia Computer Science, 117:256–265. [find](https://scholar.google.com/scholar?q=Abu+Bakr+Soliman%2C+Kareem+Eissa%2C+and+Samhaa+R+El%2DBeltagy%2E+2017%2E+Aravec%3A+A+set+of+arabic+word+embedding+models+for+use+in+arabic+nlp%2E+Procedia+Computer+Science%2C+117%3A256%E2%80%93265%2E)
37. Ellen Spertus. 1997. Smokey: Automatic recognition of hostile messages. In Aaai/iaai, pages 1058–1065. [find](https://scholar.google.com/scholar?q=Ellen+Spertus%2E+1997%2E+Smokey%3A+Automatic+recognition+of+hostile+messages%2E+In+Aaai%2Fiaai%2C+pages+1058%E2%80%931065%2E)
38. Hui-Po Su, Zhen-Jie Huang, Hao-Tsung Chang, and Chuan-Jie Lin. 2017. Rephrasing profanity in chinese text. In Proceedings of the First Workshop on Abusive Language Online, pages 18–24. [find](https://scholar.google.com/scholar?q=Hui%2DPo+Su%2C+Zhen%2DJie+Huang%2C+Hao%2DTsung+Chang%2C+and+Chuan%2DJie+Lin%2E+2017%2E+Rephrasing+profanity+in+chinese+text%2E+In+Proceedings+of+the+First+Workshop+on+Abusive+Language+Online%2C+pages+18%E2%80%9324%2E)
39. Phuong Thi Tran et al. 2019. On the convergence proof of amsgrad and a new version. IEEE Access, 7:61706– 61716. [↗](https://doi.org/10.1109/access.2019.2916341)
40. Chong Ho Yu. 1977. Exploratory data analysis. Methods, 2:131–160. [find](https://scholar.google.com/scholar?q=Chong+Ho+Yu%2E+1977%2E+Exploratory+data+analysis%2E+Methods%2C+2%3A131%E2%80%93160%2E)
41. Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar. 2019a. [Predicting the Type and Target of Offensive Posts in Social Media](https://md.research.elamur.ai/free/en/papers/zampieri-2019-predicting-type-target-offensive-posts/). In Proceedings of NAACL.
42. Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar. 2019b. [Semeval-2019 task 6: Identifying and categorizing offensive language in social media (offenseval)](https://md.research.elamur.ai/free/en/papers/zampieri-2019-semeval-2019-task-6-identifying/). In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 75–86.
43. Marcos Zampieri, Preslav Nakov, Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, Hamdy Mubarak, Leon Derczynski, Zeses Pitenis, and Çağrı Çöltekin. 2020. SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020). In Proceedings of SemEval. [↗](https://doi.org/10.48550/arxiv.2006.07235)
44. Jian Zhu, Zuoyu Tian, and Sandra Kübler. 2019. UM-IU@LING at SemEval-2019 task 6: Identifying offensive tweets using BERT and SVMs. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 788–795, Minneapolis, Minnesota, USA, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jian+Zhu%2C+Zuoyu+Tian%2C+and+Sandra+Ku%CC%88bler%2E+2019%2E+UM%2DIU%40LING+at+SemEval%2D2019+task+6%3A+Identifying+offensive+tweets+using+BERT+and+SVMs%2E+In+Proceedings+of+the+13th+International+Workshop+on+Semantic+Evalu)

*Updated 1 November 2026*